कृषि में कृत्रिम बुद्धिमत्ता
Global population by 2050 is expected to reach more than nine billion. Raise in population may create a huge food demand and to fulfil the food security which will require an increase in agricultural production by 70%. So we have to get more produce from limited land and also by reducing the cost of cultivation.
New technologies will be needed to ease the workload on farmers. Field operations will be remotely controlled and automated risk will be identified throughout the crop cycle. This machine learning also develops farmers’ friendly apps to ease the workload of farmers and to improve a wide range of agriculture related risk.
The raise in cost of cultivation, crop failures due to unpredictable diseases, loss of soil fertility and labour shortage has significant negative impact in agriculture. Increasing in demand and shortage of supply adversely affect the socio economic status. Machine learning and artificial intelligence attain its importance to overcome this strategy.
Artificial intelligence is the intelligence exhibited by machines, rather than human or other animals. The action to maximize the success will be carried out by using the intelligent agents which perceives it’s environment (Russel et al., 2015). Artificial intelligence pave the way towards drones, robotics and sensor based technologies. Certain apps like plantix, ICRISAT sowing app etc guides farmers throughout the process of, sowing, disease and pest management, harvesting and sale of produce.
AI based machines in Agriculture
Drones
Drones have the potential to address major challenges in agriculture. It gives a high tech makeover in agriculture. It is used throughout the life cycle of crop. Crop will be scanned using both visible and near infrared light drone-carried devices can help track changes in plants and indicate their health and alert farmers to diseases.
Planting and spraying is faster with drones than traditional machinery. Drone is one platform that allows the field to be sensed multiple times throughout the growing season for identifying the ideal timing for in-season fertilizer application (Thompson et al., 2017). Piloted agricultural aircraft like unmanned aerial vehicles are remotely controlled for crop production.
Robotics
Robotics is a new trend in agriculture. It is performing various agricultural operations autonomously such as spraying, weed control, fruit picking, and manage individual plants in novel ways. Blue River technology is founded in 2011. It is a California-based startup combines artificial intelligence, computer vision and robotics .
Computer vision system identifies each individual plant, and robotics enables smart machines to work. See and spray is robot developed by blue river technology for efficient weed management The use of sensors that detect weeds, the type of weeds and the right herbicides are sprayed precisely as per encroachment area.
Robots are also used in lawns to cut the grass (Demeter). The higher quality products can be sensed by machines (colour, weight, density, ripeness, size, shape) accurately. More than 90% of the fruits were detected to harvest by robot moreover, the robot could harvest a fruit in 16s (Onishi et al., 2019).
Wireless sensor network
Network of devices that can communicate the information gathered from a monitored field through wireless links. Various sensor nodes will be placed in the field for monitoring the operations. Sensor based irrigation scheduling can be done according to the sensor data .
The moisture percentage will be available in smart phones of farmers automatically through message. Gravimetric method is cumbersome. So by sensor data it is ease to farmers to schedule the irrigation according to the depletion of moisture content.
Mobile apps
Plantix:
Berlin based start up to detect the defects and nutrient deficiencies. This app uses images to detect the diseases and then a diagnosis of the plant health is provided. Initially launched in the Indian regional languages of Telugu and Hindi.30 crops and offers prescriptions for over 120 crop diseases.
Prospera:
This Israeli based startup was founded in 2014. It guides the farmers by collecting the data that farmers have like soil/water sensors, aerial images and so on. The Prospera device can be used in green houses also
The Sowing App
Microsoft in partnership with ICRISAT developed sowing app .It uses artificial intelligence and crop modelling tools provide farmers customized real time advisories. Helps to define optimal sowing timings. Customized messages will be sent to the farmers that advises them on farm operations to carry out.
Challenges
Even though machine learning has vast opportunities there still exists a lack of familiarity with machines. Lot of data is required to train the machines for precise predictions but it’s very hard to get the temporal data. To explore the enormous scope of artificial intelligence in agriculture, applications need to be more robust.
The solutions need to become more affordable so that the technology will reaches the masses. The solution will be more affordable in open source platform, the greatest challenge is to make the solutions having higher penetration among the farmers.
Conclusion
Smart farming practices can be developed using artificial intelligence to minimize cost of cultivation, loss of farmers and to provide them with high yield. Crop production may be done better and cheaper by using artificial intelligence based technologies.
Such technologies will reduce labour efforts and also it guides farmers throughout the crop cycle .
References
Russell, S., Dewey, D., & Tegmark, M. (2015). Research priorities for robust and beneficial artificial intelligence. Ai Magazine, 36(4): 105-114.
Thompson, L.J. 2017. Using drone based sensors to direct variable-rate, in-season, aerial nitrogen application on corn. International conference on Ad-hoc and networks and wireless. 165-174.
Onishi, Y., Yoshida, T., Kurita, H., Fukao, T., Arihara, H., & Iwai, A. (2019). An automated fruit harvesting robot by using deep learning. ROBOMECH Journal, 6(1):13.
Authors
Durga C.
Dept. of Agronomy, Kerala Agricultural University,
Vellanikkara, Thrissur, Kerala (680 656), India
email: